DOI QR코드

DOI QR Code

A Proposal of Remaining Useful Life Prediction Model for Turbofan Engine based on k-Nearest Neighbor

k-NN을 활용한 터보팬 엔진의 잔여 유효 수명 예측 모델 제안

  • Received : 2021.01.05
  • Accepted : 2021.04.02
  • Published : 2021.04.30

Abstract

The maintenance industry is mainly progressing based on condition-based maintenance after corrective maintenance and preventive maintenance. In condition-based maintenance, maintenance is performed at the optimum time based on the condition of equipment. In order to find the optimal maintenance point, it is important to accurately understand the condition of the equipment, especially the remaining useful life. Thus, using simulation data (C-MAPSS), a prediction model is proposed to predict the remaining useful life of a turbofan engine. For the modeling process, a C-MAPSS dataset was preprocessed, transformed, and predicted. Data pre-processing was performed through piecewise RUL, moving average filters, and standardization. The remaining useful life was predicted using principal component analysis and the k-NN method. In order to derive the optimal performance, the number of principal components and the number of neighbor data for the k-NN method were determined through 5-fold cross validation. The validity of the prediction results was analyzed through a scoring function while considering the usefulness of prior prediction and the incompatibility of post prediction. In addition, the usefulness of the RUL prediction model was proven through comparison with the prediction performance of other neural network-based algorithms.

정비 산업은 사후정비, 예방정비를 거쳐, 상태기반 정비를 중심으로 진행되고 있다. 상태기반 정비는 장비의 상태를 파악하여, 최적 시점에서의 정비를 수행한다. 최적의 정비 시점을 찾기 위해서는 장비의 상태, 즉 잔여 유효 수명을 정확하게 파악하는 것이 중요하다. 이에, 본 논문은 시뮬레이션 데이터(C-MAPSS)를 사용한 터보팬 엔진의 잔여 유효수명(RUL, Remaining Useful Life) 예측 모델을 제시한다. 모델링을 위해 C-MAPSS(Commercial Modular Aero-Propulsion System Simulation) 데이터를 전처리, 변환, 예측하는 과정을 거쳤다. RUL 임계값 설정, 이동평균필터 및 표준화를 통해 데이터 전처리를 수행하였고, 주성분 분석(Principal Component Analysis)과 k-NN(k-Nearest Neighbor)을 활용하여 잔여 유효 수명을 예측하였다. 최적의 성능을 도출하기 위해, 5겹 교차검증기법을 통해 최적의 주성분 개수 및 k-NN의 근접 데이터 개수를 결정하였다. 또한, 사전 예측의 유용성, 사후 예측의 부적합성을 고려한 스코어링 함수(Scoring Function)를 통해 예측 결과를 분석하였다. 마지막으로, 현재까지 제시되어온 뉴럴 네트워크 기반의 알고리즘과 예측 성능 비교 및 분석을 통해 k-NN 활용 모델의 유용성을 검증하였다.

Keywords

References

  1. J. H. Choi, "Introduction of Failure Prediction and Prognostics Health Management", Journal of the KSME, Vol.53, No.7, pp.24-34, Jul. 2013.
  2. S. H. Lee, B. D. Youn, "Directions for Industry 4.0, Failure Prediction and Prognostics Health Management", Journal of the KSNVE, Vol.25, No.1, pp.22-28, Feb. 2015.
  3. B.S. Seo, T. W. Hwang, B. C. Jang, J. H. Song, Y. H. Son, D. K. Lee, B. D. Youn, "Introduction of the 4th industrial revolution and success cases through PHM technology", Journal of the KSME, Vol.59, No.1, pp.32-37, Jan. 2019.
  4. X. Jia, B. Huang, J. Feng, H. Cai, J. Lee, "A Review of PHM Data Competitions from 2008 to 2017", Annual Conference of the PHM Society, Vol.10, No.1, Sep. 2018. DOI: https://doi.org/10.36001/phmconf.2018.v10i1.462
  5. G. S. Babu, P. Zhao, X. Li, "Deep Convolutional Neural Network Based Regression Approach for Estimation of Remaining Useful Life", Database Systems for Advanced Application. DASFAA, pp.214-228, Mar. 2016. DOI: https://doi.org/10.1007/978-3-319-32025-0_14
  6. Heimes, F., "Recurrent neural networks for remaining useful life estimation", Intenational Conference on Prognostics and Health Management, IEEE, Dever, CO, pp.1-6, Oct. 2008. DOI: https://doi.org/10.1109/PHM.2008.4711422
  7. Y. Yun, S, Kim, S. H. Cho, J. H. Choi, "Neural Network based Aircraft Engine Health Management using C-MAPSS Data", Journal of Aerospace System Engineering, Vol.13, No.6, pp.17-25, 2019. DOI: https://dx.doi.org/10.20910/JASE.2019.13.6.17
  8. Peel, L., "Data driven prognostics using a Kalman filter ensemble of neural network models", Intenational conference on Prognostics and Health Management, Denver, CO, pp. 1-6, 2008. DOI: https://doi.org/10.1109/phm.2008.4711423
  9. P. Lim, C. K. Goh, K. C. Tan, A time-window neural networks based framework for remaining useful life estimation, International Joint Conference on Neural Networks(IJCNN), Vancouver, BC, pp.1746-1753, 2016. DOI: https://doi.org/10.1109/IJCNN.2016.7727410
  10. Markus G., Deep learning: a critical appraisal, arXiv:1801.00631, pp.5-14, 2018.
  11. H. T. Yang, H. Jhang, "Present and future of deep learning", FUTURE HORIZON, No.38, pp.8-11, 2018
  12. A. Saxena, and K. Goebel, PHM08 Challenge Data Set, NASA Ames Prognostics Data Repository NASA Ames Research Center, Moffett Field, CA, 2008.
  13. K. Beyer, J. Goldstein, R. Ramakrishnan, U. Shaft, "When Is "Nearest Neighbor" meaningful?", International Conference on Database Theory, ICDT, pp.217-235, Jan. 1997. DOI: https://doi.org/10.1007/3-540-49257-7_15
  14. T. Wong and P. Yeh, "Reliable Accuracy Estimates from k-fold Cross Validation", IEEE Transactions on Knowledge and Data Engineering, Vol.32, No.8, pp.1586-1594, Aug. 2020. DOI: https://doi.org/10.1109/TKDE.2019.2912815